Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit dc6c9a35 authored by Kirill A. Shutemov's avatar Kirill A. Shutemov Committed by Linus Torvalds
Browse files

mm: account pmd page tables to the process



Dave noticed that unprivileged process can allocate significant amount of
memory -- >500 MiB on x86_64 -- and stay unnoticed by oom-killer and
memory cgroup.  The trick is to allocate a lot of PMD page tables.  Linux
kernel doesn't account PMD tables to the process, only PTE.

The use-cases below use few tricks to allocate a lot of PMD page tables
while keeping VmRSS and VmPTE low.  oom_score for the process will be 0.

	#include <errno.h>
	#include <stdio.h>
	#include <stdlib.h>
	#include <unistd.h>
	#include <sys/mman.h>
	#include <sys/prctl.h>

	#define PUD_SIZE (1UL << 30)
	#define PMD_SIZE (1UL << 21)

	#define NR_PUD 130000

	int main(void)
	{
		char *addr = NULL;
		unsigned long i;

		prctl(PR_SET_THP_DISABLE);
		for (i = 0; i < NR_PUD ; i++) {
			addr = mmap(addr + PUD_SIZE, PUD_SIZE, PROT_WRITE|PROT_READ,
					MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
			if (addr == MAP_FAILED) {
				perror("mmap");
				break;
			}
			*addr = 'x';
			munmap(addr, PMD_SIZE);
			mmap(addr, PMD_SIZE, PROT_WRITE|PROT_READ,
					MAP_ANONYMOUS|MAP_PRIVATE|MAP_FIXED, -1, 0);
			if (addr == MAP_FAILED)
				perror("re-mmap"), exit(1);
		}
		printf("PID %d consumed %lu KiB in PMD page tables\n",
				getpid(), i * 4096 >> 10);
		return pause();
	}

The patch addresses the issue by account PMD tables to the process the
same way we account PTE.

The main place where PMD tables is accounted is __pmd_alloc() and
free_pmd_range(). But there're few corner cases:

 - HugeTLB can share PMD page tables. The patch handles by accounting
   the table to all processes who share it.

 - x86 PAE pre-allocates few PMD tables on fork.

 - Architectures with FIRST_USER_ADDRESS > 0. We need to adjust sanity
   check on exit(2).

Accounting only happens on configuration where PMD page table's level is
present (PMD is not folded).  As with nr_ptes we use per-mm counter.  The
counter value is used to calculate baseline for badness score by
oom-killer.

Signed-off-by: default avatarKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reported-by: default avatarDave Hansen <dave.hansen@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Reviewed-by: default avatarCyrill Gorcunov <gorcunov@openvz.org>
Cc: Pavel Emelyanov <xemul@openvz.org>
Cc: David Rientjes <rientjes@google.com>
Tested-by: default avatarSedat Dilek <sedat.dilek@gmail.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 8aa76875
Loading
Loading
Loading
Loading
+6 −6
Original line number Diff line number Diff line
@@ -555,12 +555,12 @@ this is causing problems for your system/application.

oom_dump_tasks

Enables a system-wide task dump (excluding kernel threads) to be
produced when the kernel performs an OOM-killing and includes such
information as pid, uid, tgid, vm size, rss, nr_ptes, swapents,
oom_score_adj score, and name.  This is helpful to determine why the
OOM killer was invoked, to identify the rogue task that caused it,
and to determine why the OOM killer chose the task it did to kill.
Enables a system-wide task dump (excluding kernel threads) to be produced
when the kernel performs an OOM-killing and includes such information as
pid, uid, tgid, vm size, rss, nr_ptes, nr_pmds, swapents, oom_score_adj
score, and name.  This is helpful to determine why the OOM killer was
invoked, to identify the rogue task that caused it, and to determine why
the OOM killer chose the task it did to kill.

If this is set to zero, this information is suppressed.  On very
large systems with thousands of tasks it may not be feasible to dump
+9 −5
Original line number Diff line number Diff line
@@ -190,7 +190,7 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)

#endif	/* CONFIG_X86_PAE */

static void free_pmds(pmd_t *pmds[])
static void free_pmds(struct mm_struct *mm, pmd_t *pmds[])
{
	int i;

@@ -198,10 +198,11 @@ static void free_pmds(pmd_t *pmds[])
		if (pmds[i]) {
			pgtable_pmd_page_dtor(virt_to_page(pmds[i]));
			free_page((unsigned long)pmds[i]);
			mm_dec_nr_pmds(mm);
		}
}

static int preallocate_pmds(pmd_t *pmds[])
static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[])
{
	int i;
	bool failed = false;
@@ -215,11 +216,13 @@ static int preallocate_pmds(pmd_t *pmds[])
			pmd = NULL;
			failed = true;
		}
		if (pmd)
			mm_inc_nr_pmds(mm);
		pmds[i] = pmd;
	}

	if (failed) {
		free_pmds(pmds);
		free_pmds(mm, pmds);
		return -ENOMEM;
	}

@@ -246,6 +249,7 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)

			paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT);
			pmd_free(mm, pmd);
			mm_dec_nr_pmds(mm);
		}
	}
}
@@ -283,7 +287,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)

	mm->pgd = pgd;

	if (preallocate_pmds(pmds) != 0)
	if (preallocate_pmds(mm, pmds) != 0)
		goto out_free_pgd;

	if (paravirt_pgd_alloc(mm) != 0)
@@ -304,7 +308,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
	return pgd;

out_free_pmds:
	free_pmds(pmds);
	free_pmds(mm, pmds);
out_free_pgd:
	free_page((unsigned long)pgd);
out:
+6 −3
Original line number Diff line number Diff line
@@ -21,7 +21,7 @@

void task_mem(struct seq_file *m, struct mm_struct *mm)
{
	unsigned long data, text, lib, swap;
	unsigned long data, text, lib, swap, ptes, pmds;
	unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;

	/*
@@ -42,6 +42,8 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
	text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
	lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
	swap = get_mm_counter(mm, MM_SWAPENTS);
	ptes = PTRS_PER_PTE * sizeof(pte_t) * atomic_long_read(&mm->nr_ptes);
	pmds = PTRS_PER_PMD * sizeof(pmd_t) * mm_nr_pmds(mm);
	seq_printf(m,
		"VmPeak:\t%8lu kB\n"
		"VmSize:\t%8lu kB\n"
@@ -54,6 +56,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
		"VmExe:\t%8lu kB\n"
		"VmLib:\t%8lu kB\n"
		"VmPTE:\t%8lu kB\n"
		"VmPMD:\t%8lu kB\n"
		"VmSwap:\t%8lu kB\n",
		hiwater_vm << (PAGE_SHIFT-10),
		total_vm << (PAGE_SHIFT-10),
@@ -63,8 +66,8 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
		total_rss << (PAGE_SHIFT-10),
		data << (PAGE_SHIFT-10),
		mm->stack_vm << (PAGE_SHIFT-10), text, lib,
		(PTRS_PER_PTE * sizeof(pte_t) *
		 atomic_long_read(&mm->nr_ptes)) >> 10,
		ptes >> 10,
		pmds >> 10,
		swap << (PAGE_SHIFT-10));
}

+24 −0
Original line number Diff line number Diff line
@@ -1438,8 +1438,32 @@ static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud,
{
	return 0;
}

static inline unsigned long mm_nr_pmds(struct mm_struct *mm)
{
	return 0;
}

static inline void mm_inc_nr_pmds(struct mm_struct *mm) {}
static inline void mm_dec_nr_pmds(struct mm_struct *mm) {}

#else
int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address);

static inline unsigned long mm_nr_pmds(struct mm_struct *mm)
{
	return atomic_long_read(&mm->nr_pmds);
}

static inline void mm_inc_nr_pmds(struct mm_struct *mm)
{
	atomic_long_inc(&mm->nr_pmds);
}

static inline void mm_dec_nr_pmds(struct mm_struct *mm)
{
	atomic_long_dec(&mm->nr_pmds);
}
#endif

int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
+2 −1
Original line number Diff line number Diff line
@@ -363,7 +363,8 @@ struct mm_struct {
	pgd_t * pgd;
	atomic_t mm_users;			/* How many users with user space? */
	atomic_t mm_count;			/* How many references to "struct mm_struct" (users count as 1) */
	atomic_long_t nr_ptes;			/* Page table pages */
	atomic_long_t nr_ptes;			/* PTE page table pages */
	atomic_long_t nr_pmds;			/* PMD page table pages */
	int map_count;				/* number of VMAs */

	spinlock_t page_table_lock;		/* Protects page tables and some counters */
Loading